factual
Models improve 25-30% per year on valuable tasks
The rate of model improvement at economically valuable tasks is roughly 25-30 percent per year; GPT-5 now scores 64 percent on APEX, up from GPT-4o a year ago, though sustaining that rate would be challenging.
factualpending
Speaker
Brendan FoodyEvidence Quote
“call it a 25 percent–, 30 percent–improvement. Per year, exactly. Now, GPT-5 is at 64 percent”
Created: 6/12/2026, 4:53:54 PM
Your notes
Loading notes...